INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Siber

-0.73

 Conclusion

-0.72

-0.69

CONCLUS

-0.66

phalt

-0.65

vertisement

-0.64

leans

-0.64

articles

-0.64

 Niet

-0.63

Catal

-0.63

POSITIVE LOGITS

deen

0.71

 Lennon

0.64

 bisc

0.63

 cones

0.62

 joint

0.62

lag

0.62

xus

0.61

Caf

0.61

lder

0.61

igham

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.